The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution

• URL: http://arxiv.org/abs/2605.22635v2
• Date: Fri, 22 May 2026 04:42:51 GMT
• Title: The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
• Abstract summary: We introduce Conflict-Averse Magnitude-Enhanced Gradient Descent (CAME-Grad)<n>CAME-Grad is a universal plug-and-play radiology report generation tool.<n>It brings substantial and consistent improvements across eight diverse RRG methods.
• Score: 21.473137939180333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While multi-task learning based automatic radiology report generation (RRG) is widely adopted to ensure clinical consistency, most focus on architectural designs yet remain limited to coarse linear scalarization strategies. These strategies cannot effectively balance the hard constraints of discriminative clinical supervision with the smoothness requirements of report generation. To address these problems, we analyze the failure mechanism of linear scalarization from the perspective of gradient dynamics, utilizing the stochastic differential equation (SDE) framework to characterize it as a "Double Dilemma" of drift term deviation and diffusion term decay. Based on this, we propose a backbone-agnostic optimizer named Conflict-Averse Magnitude-Enhanced Gradient Descent (CAME-Grad). Through conflict-averse direction rectification and magnitude-enhanced energy injection, the algorithm not only ensures geometric validity, but also avoids local optimal solutions. Then, the adaptive gradient fusion mechanism is used to establish a dynamic balance between the theoretical optimal direction and the task-specific inductive bias. Experiments show that as a universal plug-and-play optimizer, CAME-Grad brings substantial and consistent improvements across eight diverse RRG methods, elevating overall clinical efficacy performance by an average of 2.3% on MIMIC-CXR and 1.9% on IU X-Ray. Our code is available at https://github.com/vpsg-research/CAME-Grad.

Related papers

• A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE Solvers [5.821193246951147]
  Physics-informed neural networks (PINNs) represent a growing frontier using artificial intelligence to solve partial differential equations (PDEs)<n>We conduct systematic experiments across a wide spectrum of problems, from simple linear Poisson to high-Mach hypersonic flows with strong discontinuities.<n>Our results reveal a consistent trend: as nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced.
  arXiv  Detail & Related papers  (2026-09-07T12:44:35Z)
• Effective Covariance Dynamics in Solvable High-Dimensional GANs [2.639628765667673]
  We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data.<n>We prove that the microscopic training process converges, in the high-dimensional limit, to deterministic ordinary differential equations governed by this effective covariance.
  arXiv  Detail & Related papers  (2026-06-25T16:33:54Z)
• Resolving gradient pathology in physics-informed epidemiological models [0.0]
  We propose a novel method, conflict-gated gradient scaling (CGGS), to address gradient conflicts in physics-informed neural networks for epidemiological modelling.<n>Unlike schemes that only normalize, CGGS acts as it suppresses the physical constraint when conflict is high, allowing to prioritize data fidelity.
  arXiv  Detail & Related papers  (2026-03-25T00:19:21Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening [11.791358860917189]
  deep learning methods for remote sensing pansharpening have advanced rapidly.<n>Many existing methods struggle to fully leverage feature heterogeneity and redundancy.<n>We introduce a general adaptive dual-level weighting mechanism (ADWM) to address these challenges.
  arXiv  Detail & Related papers  (2025-03-17T14:24:00Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation [73.83178465971552]
  The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. We propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective.
  arXiv  Detail & Related papers  (2023-07-27T08:58:05Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Cogradient Descent for Dependable Learning [64.02052988844301]
  We propose a dependable learning based on Cogradient Descent (CoGD) algorithm to address the bilinear optimization problem. CoGD is introduced to solve bilinear problems when one variable is with sparsity constraint. It can also be used to decompose the association of features and weights, which further generalizes our method to better train convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-06-20T04:28:20Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.